split_font · Mcp Font Split MCP: Risk & Policy

WHAT IT DOES

What split_font does on Mcp Font Split

AI agents use split_font to create or update resources in Mcp Font Split — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Font Split environment.

WHY IT NEEDS A POLICY

Why split_font needs a policy

The tool reads an input font file and writes multiple output files (WOFF2 chunks + CSS). This is a Write operation — it creates new files on disk. It is reversible in the sense that the generated files can be deleted. The blast radius is medium because it writes potentially many files into the workspace, but it does not delete originals or execute arbitrary code.

From the tool's definition 'This writes output files' and 'split one local TTF/OTF/TTC/OTC/WOFF/WOFF2 font into cn-font-split web font output files'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

split_font Rate-limited

split_font stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "split_font": {
      "limits": [
        {
          "counter": "split_font_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Font Split, so you can run agents against it safely.

FAQ

Questions about split_font

What does the split_font tool do? +

Call this when the user wants to split one local TTF/OTF/TTC/OTC/WOFF/WOFF2 font into cn-font-split web font output files. This writes output files; inspect resultType, outputMode, performedSplit, usedFallback, warnings, and manifestPath before claiming success. All paths must stay inside the configured font workspace. It is categorised as a Write tool in the Mcp Font Split MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on split_font? +

Register the Mcp Font Split MCP server in PolicyLayer and add a rule for split_font: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Font Split. Nothing to install.

What risk level is split_font? +

split_font is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit split_font? +

Yes. Add a rate_limit block to the split_font rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block split_font completely? +

Set action: deny in the PolicyLayer policy for split_font. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides split_font? +

split_font is provided by the Mcp Font Split MCP server (wenzhimo/mcp-font-split). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.